|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "markdown", |
| 5 | + "id": "5214b543", |
| 6 | + "metadata": {}, |
| 7 | + "source": [ |
| 8 | + "- Load two eval_results\n", |
| 9 | + "\n", |
| 10 | + "EvalResult\n", |
| 11 | + "- example, label, result, item_summary" |
| 12 | + ] |
| 13 | + }, |
| 14 | + { |
| 15 | + "cell_type": "code", |
| 16 | + "execution_count": null, |
| 17 | + "id": "314bb6b4", |
| 18 | + "metadata": {}, |
| 19 | + "outputs": [], |
| 20 | + "source": [ |
| 21 | + "import time\n", |
| 22 | + "import typing\n", |
| 23 | + "import weave\n", |
| 24 | + "import random\n", |
| 25 | + "import string\n", |
| 26 | + "from weave import weave_internal\n", |
| 27 | + "weave.use_frontend_devmode()\n", |
| 28 | + "from weave.panels import panel_board\n", |
| 29 | + "from weave import ops_domain" |
| 30 | + ] |
| 31 | + }, |
| 32 | + { |
| 33 | + "cell_type": "code", |
| 34 | + "execution_count": null, |
| 35 | + "id": "550daef6", |
| 36 | + "metadata": {}, |
| 37 | + "outputs": [], |
| 38 | + "source": [ |
| 39 | + "def rand_string_n(n: int) -> str:\n", |
| 40 | + " return \"\".join(\n", |
| 41 | + " random.choice(string.ascii_uppercase + string.digits) for _ in range(n)\n", |
| 42 | + " )\n", |
| 43 | + "\n", |
| 44 | + "dataset_raw = [{\n", |
| 45 | + " 'id': str(i),\n", |
| 46 | + " 'example': rand_string_n(10),\n", |
| 47 | + " 'label': random.choice(string.ascii_uppercase)} for i in range(50)]\n", |
| 48 | + "dataset = weave.save(dataset_raw, 'dataset')\n", |
| 49 | + "#dataset" |
| 50 | + ] |
| 51 | + }, |
| 52 | + { |
| 53 | + "cell_type": "code", |
| 54 | + "execution_count": null, |
| 55 | + "id": "d0d930d8", |
| 56 | + "metadata": {}, |
| 57 | + "outputs": [], |
| 58 | + "source": [ |
| 59 | + "def predict(dataset_row, config):\n", |
| 60 | + " if random.random() < config['correct_chance']:\n", |
| 61 | + " return dataset_row['label']\n", |
| 62 | + " return random.choice(string.ascii_uppercase)" |
| 63 | + ] |
| 64 | + }, |
| 65 | + { |
| 66 | + "cell_type": "code", |
| 67 | + "execution_count": null, |
| 68 | + "id": "eb86b95c", |
| 69 | + "metadata": {}, |
| 70 | + "outputs": [], |
| 71 | + "source": [ |
| 72 | + "def evaluate(dataset, predict_config):\n", |
| 73 | + " eval_result = []\n", |
| 74 | + " correct_count = 0\n", |
| 75 | + " count = 0\n", |
| 76 | + " for dataset_row in dataset:\n", |
| 77 | + " start_time = time.time()\n", |
| 78 | + " result = predict(dataset_row, predict_config)\n", |
| 79 | + " latency = time.time() - start_time\n", |
| 80 | + " latency = random.gauss(predict_config['latency_mu'], predict_config['latency_sigma'])\n", |
| 81 | + " correct = dataset_row['label'] == result\n", |
| 82 | + " if correct:\n", |
| 83 | + " correct_count += 1\n", |
| 84 | + " count +=1 \n", |
| 85 | + " eval_result.append({\n", |
| 86 | + " 'dataset_id': dataset_row['id'],\n", |
| 87 | + " 'result': result,\n", |
| 88 | + " 'summary': {\n", |
| 89 | + " 'latency': latency,\n", |
| 90 | + " 'correct': correct\n", |
| 91 | + " }\n", |
| 92 | + " })\n", |
| 93 | + " return {\n", |
| 94 | + " 'config': predict_config,\n", |
| 95 | + " 'eval_table': eval_result,\n", |
| 96 | + " 'summary': {'accuracy': correct_count / len(dataset)}}" |
| 97 | + ] |
| 98 | + }, |
| 99 | + { |
| 100 | + "cell_type": "code", |
| 101 | + "execution_count": null, |
| 102 | + "id": "05d16a5e", |
| 103 | + "metadata": {}, |
| 104 | + "outputs": [], |
| 105 | + "source": [ |
| 106 | + "eval_result_raw0 = evaluate(dataset_raw, {'correct_chance': 0.5, 'latency_mu': 0.3, 'latency_sigma': 0.1})\n", |
| 107 | + "eval_result_raw1 = evaluate(dataset_raw, {'correct_chance': 0.5, 'latency_mu': 0.4, 'latency_sigma': 0.2})\n", |
| 108 | + "eval_result0 = weave.save(eval_result_raw0, 'eval_result0')\n", |
| 109 | + "eval_result1 = weave.save(eval_result_raw1, 'eval_result1')" |
| 110 | + ] |
| 111 | + }, |
| 112 | + { |
| 113 | + "cell_type": "code", |
| 114 | + "execution_count": null, |
| 115 | + "id": "e8065ad6", |
| 116 | + "metadata": {}, |
| 117 | + "outputs": [], |
| 118 | + "source": [ |
| 119 | + "\n", |
| 120 | + "\n", |
| 121 | + "varbar = panel_board.varbar()\n", |
| 122 | + "\n", |
| 123 | + "dataset_var = varbar.add('dataset', dataset)\n", |
| 124 | + "eval_result0_var = varbar.add('eval_result0', eval_result0)\n", |
| 125 | + "eval_result1_var = varbar.add('eval_result1', eval_result1)\n", |
| 126 | + "\n", |
| 127 | + "summary = varbar.add('summary', weave.ops.make_list(\n", |
| 128 | + " a=weave.ops.TypedDict.merge(weave.ops.dict_(name='res0'), eval_result0_var['summary']),\n", |
| 129 | + " b=weave.ops.TypedDict.merge(weave.ops.dict_(name='res1'), eval_result1_var['summary']),\n", |
| 130 | + "))\n", |
| 131 | + "\n", |
| 132 | + "weave.ops.make_list(a=eval_result0_var['eval_table'], b=eval_result0_var['eval_table'])\n", |
| 133 | + "\n", |
| 134 | + "concatted_evals = varbar.add('concatted_evals', weave.ops.List.concat(\n", |
| 135 | + " weave.ops.make_list(\n", |
| 136 | + " a=eval_result0_var['eval_table'].map(\n", |
| 137 | + " lambda row: weave.ops.TypedDict.merge(\n", |
| 138 | + " weave.ops.dict_(name='res0'), row)),\n", |
| 139 | + " b=eval_result1_var['eval_table'].map(\n", |
| 140 | + " lambda row: weave.ops.TypedDict.merge(\n", |
| 141 | + " weave.ops.dict_(name='res1'), row)))))\n", |
| 142 | + "\n", |
| 143 | + "# join evals together first\n", |
| 144 | + "joined_evals = varbar.add('joined_evals', weave.ops.join_all(\n", |
| 145 | + " weave.ops.make_list(a=eval_result0_var['eval_table'], b=eval_result1_var['eval_table']),\n", |
| 146 | + " lambda row: row['dataset_id'],\n", |
| 147 | + " False))\n", |
| 148 | + "\n", |
| 149 | + "# then join dataset to evals\n", |
| 150 | + "dataset_evals = varbar.add('dataset_evals', weave.ops.join_2(\n", |
| 151 | + " dataset_var,\n", |
| 152 | + " joined_evals,\n", |
| 153 | + " lambda row: row['id'],\n", |
| 154 | + " lambda row: row['dataset_id'][0],\n", |
| 155 | + " 'dataset',\n", |
| 156 | + " 'evals',\n", |
| 157 | + " False,\n", |
| 158 | + " False\n", |
| 159 | + "))\n", |
| 160 | + "\n", |
| 161 | + "\n", |
| 162 | + "main = weave.panels.Group(\n", |
| 163 | + " layoutMode=\"grid\",\n", |
| 164 | + " showExpressions=True,\n", |
| 165 | + " enableAddPanel=True,\n", |
| 166 | + " )\n", |
| 167 | + "\n", |
| 168 | + "#### Run/config info TODO\n", |
| 169 | + "\n", |
| 170 | + "#### Summary info\n", |
| 171 | + "\n", |
| 172 | + "main.add(\"accuracy\",\n", |
| 173 | + " weave.panels.Plot(summary,\n", |
| 174 | + " x=lambda row: row['accuracy'],\n", |
| 175 | + " y=lambda row: row['name'],\n", |
| 176 | + " color=lambda row: row['name']\n", |
| 177 | + " ),\n", |
| 178 | + " layout=weave.panels.GroupPanelLayout(x=0, y=0, w=12, h=4))\n", |
| 179 | + "\n", |
| 180 | + "\n", |
| 181 | + "main.add(\"latency\",\n", |
| 182 | + " weave.panels.Plot(concatted_evals,\n", |
| 183 | + " x=lambda row: row['summary']['latency'],\n", |
| 184 | + " y=lambda row: row['name'],\n", |
| 185 | + " color=lambda row: row['name'],\n", |
| 186 | + " mark='boxplot'),\n", |
| 187 | + " layout=weave.panels.GroupPanelLayout(x=12, y=0, w=12, h=4))\n", |
| 188 | + "\n", |
| 189 | + "#ct = main.add('concat_t', concatted_evals, layout=weave.panels.GroupPanelLayout(x=0, y=4, w=24, h=12))\n", |
| 190 | + "# main.add('dataset_table', dataset)\n", |
| 191 | + "# main.add('joined_evals', joined_evals)\n", |
| 192 | + "# main.add('dataset_evals', dataset_evals, layout=weave.panels.GroupPanelLayout(x=0, y=4, w=24, h=6))\n", |
| 193 | + "\n", |
| 194 | + "##### Example details\n", |
| 195 | + "\n", |
| 196 | + "# more ideas: show examples that all got wrong, or that are confusing\n", |
| 197 | + "\n", |
| 198 | + "faceted_view = weave.panels.Facet(dataset_evals,\n", |
| 199 | + " x=lambda row: row['evals.summary'][0]['correct'],\n", |
| 200 | + " y=lambda row: row['evals.summary'][1]['correct'],\n", |
| 201 | + " select=lambda row: row.count())\n", |
| 202 | + "\n", |
| 203 | + "faceted = main.add('faceted', faceted_view, layout=weave.panels.GroupPanelLayout(x=0, y=4, w=12, h=6))\n", |
| 204 | + "\n", |
| 205 | + "main.add(\"example_latencies\",\n", |
| 206 | + " weave.panels.Plot(dataset_evals,\n", |
| 207 | + " x=lambda row: row['evals.summary']['latency'][0],\n", |
| 208 | + " y=lambda row: row['evals.summary']['latency'][1]),\n", |
| 209 | + " layout=weave.panels.GroupPanelLayout(x=12, y=4, w=12, h=6))\n", |
| 210 | + "\n", |
| 211 | + "faceted_sel = weave.panels.Table(faceted.selected())\n", |
| 212 | + "faceted_sel.config.rowSize = 2\n", |
| 213 | + "faceted_sel.add_column(lambda row: row['dataset.id'], 'id')\n", |
| 214 | + "faceted_sel.add_column(lambda row: row['dataset.example'], 'example')\n", |
| 215 | + "faceted_sel.add_column(lambda row: row['dataset.label'], 'label')\n", |
| 216 | + "faceted_sel.add_column(lambda row: weave.ops.dict_(res0=row['evals.result'][0], res1=row['evals.result'][1]), 'result')\n", |
| 217 | + "faceted_sel.add_column(lambda row: weave.ops.dict_(res0=row['evals.summary'][0]['correct'], res1=row['evals.summary'][1]['correct']), 'correct')\n", |
| 218 | + "faceted_sel.add_column(lambda row: weave.ops.dict_(res0=row['evals.summary'][0]['latency'], res1=row['evals.summary'][1]['latency']), 'latency')\n", |
| 219 | + "\n", |
| 220 | + "main.add('faceted_sel', faceted_sel, layout=weave.panels.GroupPanelLayout(x=0, y=10, w=24, h=12))\n", |
| 221 | + "\n", |
| 222 | + "weave.panels.Board(vars=varbar, panels=main)" |
| 223 | + ] |
| 224 | + } |
| 225 | + ], |
| 226 | + "metadata": { |
| 227 | + "kernelspec": { |
| 228 | + "display_name": "Python 3 (ipykernel)", |
| 229 | + "language": "python", |
| 230 | + "name": "python3" |
| 231 | + }, |
| 232 | + "language_info": { |
| 233 | + "codemirror_mode": { |
| 234 | + "name": "ipython", |
| 235 | + "version": 3 |
| 236 | + }, |
| 237 | + "file_extension": ".py", |
| 238 | + "mimetype": "text/x-python", |
| 239 | + "name": "python", |
| 240 | + "nbconvert_exporter": "python", |
| 241 | + "pygments_lexer": "ipython3", |
| 242 | + "version": "3.9.7" |
| 243 | + } |
| 244 | + }, |
| 245 | + "nbformat": 4, |
| 246 | + "nbformat_minor": 5 |
| 247 | +} |
0 commit comments